Edit: and downvotes don't change reality. It's great software, but it's not open source.
> (d) such use, reproduction, making of derivative works, display and distribution of the software is limited to non-commercial internal research and educational purposes by not-for-profit entities;
> (e) you may not use Freesurfer in research that is sponsored by a commercial entity;
> (g) you agree that this License Agreement may be terminated at any time by notice posted on Licensor applicable website if any contributor to Freesurfer with the legal right to do so demands that or compels Licensor to terminate this license.
One of the interesting hacks is to inflate the cortical surface to a sphere which enables nonlinear registration to the accuracy of human experts.
In this freesurfer sense it is the result of a training set, where an expert has delineated cortical and/or subcortical structure on a set of one or more images. If you have multiple images and you map them all into the same atlas space, you can derive a probabilistic model from this, or collapse it to a highest likelihood map or whatever you want.
The cortical and subcortical labeling algorithms used in freesurfer use such a (probabilistic) atlas as one of the inputs. GP is wishing that they could replace this with a new, presumably improved, version.
Still, it's better than AFNI...
FreeSurfer is also very influential because it offers a bunch of utility tools for doing analysis/stats on brain images and cortical surfaces, and these tools can be easily combined with other popular neuroimaging software packages.
Jokes aside, I think niche software like this is everything HN is about (at least to me). I have no knowledge of MRIs, beyond getting on last year, but seeing this had made me start to research how I would get my brain data back from the NHS to play around with it and see what idiocy I can get up to.
It's also a good example of something pretty rare: a long lived, decently made and supported project that facilitates a lot of other peoples research.